© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105612
    Prev
    Next
    INDEX
    Explanations

    living organisms and cells

    np_acts-logits-general · gemini-2.5-flash-lite

    The word "living" when it appears in text, especially when referring to organisms, cells, or life forms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kredi
    -3.28
    鵙
    -3.09
     etik
    -2.80
     sekunder
    -2.78
     teater
    -2.77
     rajut
    -2.75
     Spanyol
    -2.73
     menyen
    -2.72
    ቼ
    -2.70
     klinik
    -2.67
    POSITIVE LOGITS
     Each
    3.08
     For
    3.03
     Particularly
    2.88
     Notably
    2.80
     That
    2.80
     holistic
    2.77
     wohin
    2.75
     Much
    2.73
     During
    2.69
     Ultimately
    2.63
    Activations Density 0.015%

    No Known Activations